Python—requests模組詳解
阿新 • • 發佈：2021-07-05
1、模組說明
requests是使用Apache2 licensed 許可證的HTTP庫。
用python編寫。
比urllib2模組更簡潔。
Request支援HTTP連線保持和連線池，支援使用cookie保持會話，支援檔案上傳，支援自動響應內容的編碼，支援國際化的URL和POST資料自動編碼。
在python內建模組的基礎上進行了高度的封裝，從而使得python進行網路請求時，變得人性化，使用Requests可以輕而易舉的完成瀏覽器可有的任何操作。
現代，國際化，友好。
requests會自動實現持久連線keep-alive
2、基礎入門
1）匯入模組
import requests
2）傳送請求的簡潔
示例程式碼：獲取一個網頁（個人github）
import requests r = requests.get('https://github.com/Ranxf') # 最基本的不帶引數的get請求 r1 = requests.get(url='http://dict.baidu.com/s', params={'wd': 'python'}) # 帶引數的get請求
我們就可以使用該方式使用以下各種方法
1 requests.get('https://github.com/timeline.json') # GET請求2 requests.post('http://httpbin.org/post') # POST請求 3 requests.put('http://httpbin.org/put') # PUT請求 4 requests.delete('http://httpbin.org/delete') # DELETE請求 5 requests.head('http://httpbin.org/get') # HEAD請求 6 requests.options('http://httpbin.org/get' ) # OPTIONS請求
3）為url傳遞引數
url_params = {'key':'value'} # 字典傳遞引數，如果值為None的鍵不會被新增到url中
r = requests.get('your url',params = url_params)
print(r.url)
輸出結果：
your url?key=value
4）響應的內容
r.encoding #獲取當前的編碼 r.encoding = 'utf-8' #設定編碼 r.text #以encoding解析返回內容。字串方式的響應體，會自動根據響應頭部的字元編碼進行解碼。 r.content #以位元組形式（二進位制）返回。位元組方式的響應體，會自動為你解碼 gzip 和 deflate 壓縮。 r.headers #以字典物件儲存伺服器響應頭，但是這個字典比較特殊，字典鍵不區分大小寫，若鍵不存在則返回None r.status_code #響應狀態碼 r.raw #返回原始響應體，也就是 urllib 的 response 物件，使用 r.raw.read() r.ok # 檢視r.ok的布林值便可以知道是否登陸成功 #*特殊方法*# r.json() #Requests中內建的JSON解碼器，以json形式返回,前提返回的內容確保是json格式的，不然解析出錯會拋異常 r.raise_for_status() #失敗請求(非200響應)丟擲異常
post傳送json請求：
import requests import json r = requests.post('https://api.github.com/some/endpoint', data=json.dumps({'some': 'data'})) print(r.json())
5）定製頭和cookie資訊
header = {'user-agent': 'my-app/0.0.1''}
cookie = {'key':'value'}
r = requests.get/post('your url',headers=header,cookies=cookie)
data = {'some': 'data'}
headers = {'content-type': 'application/json',
'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:22.0) Gecko/20100101 Firefox/22.0'}
r = requests.post('https://api.github.com/some/endpoint', data=data, headers=headers)
print(r.text)
6）響應狀態碼
使用requests方法後，會返回一個response物件，其儲存了伺服器響應的內容，如上例項中已經提到的 r.text、r.status_code……
獲取文字方式的響應體例項：當你訪問 r.text 之時，會使用其響應的文字編碼進行自動解碼，並且你可以修改其編碼讓 r.text 使用自定義的編碼進行解碼。
r = requests.get('http://www.itwhy.org') print(r.text, '\n{}\n'.format('*'*79), r.encoding) r.encoding = 'GBK' print(r.text, '\n{}\n'.format('*'*79), r.encoding)
示例程式碼：
import requests r = requests.get('https://github.com/Ranxf') # 最基本的不帶引數的get請求 print(r.status_code) # 獲取返回狀態 r1 = requests.get(url='http://dict.baidu.com/s', params={'wd': 'python'}) # 帶引數的get請求 print(r1.url) print(r1.text) # 列印解碼後的返回資料
執行結果：
/usr/bin/python3.5 /home/rxf/python3_1000/1000/python3_server/python3_requests/demo1.py 200 http://dict.baidu.com/s?wd=python ………… Process finished with exit code 0
r.status_code #如果不是200，可以使用 r.raise_for_status() 丟擲異常
7）響應
r.headers #返回字典型別,頭資訊 r.requests.headers #返回傳送到伺服器的頭資訊 r.cookies #返回cookie r.history #返回重定向資訊,當然可以在請求時加上allow_redirects = false 阻止重定向
8）超時
r = requests.get('url',timeout=1) #設定秒數超時，僅對於連線有效
9)會話物件，能夠跨請求保持某些引數
s = requests.Session() # cookies或者session或者token保存於session物件中 s.auth = ('auth','passwd') s.headers = {'key':'value'} r = s.get('url') r1 = s.get('url1')
10）代理
proxies = {'http':'ip1','https':'ip2'}
requests.get('url',proxies=proxies) # 請求時，通過代理可設定抓包
彙總：
# HTTP請求型別 # get型別 r = requests.get('https://github.com/timeline.json') # post型別 r = requests.post("http://m.ctrip.com/post") # put型別 r = requests.put("http://m.ctrip.com/put") # delete型別 r = requests.delete("http://m.ctrip.com/delete") # head型別 r = requests.head("http://m.ctrip.com/head") # options型別 r = requests.options("http://m.ctrip.com/get") # 獲取響應內容 print(r.content) #以位元組的方式去顯示，中文顯示為字元 print(r.text) #以文字的方式去顯示 #URL傳遞引數 payload = {'keyword': '香港', 'salecityid': '2'} r = requests.get("http://m.ctrip.com/webapp/tourvisa/visa_list", params=payload) print（r.url） #示例為http://m.ctrip.com/webapp/tourvisa/visa_list?salecityid=2&keyword=香港 #獲取/修改網頁編碼 r = requests.get('https://github.com/timeline.json') print （r.encoding） #json處理 r = requests.get('https://github.com/timeline.json') print（r.json()） # 需要先import json # 定製請求頭 url = 'http://m.ctrip.com' headers = {'User-Agent' : 'Mozilla/5.0 (Linux; Android 4.2.1; en-us; Nexus 4 Build/JOP40D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166 Mobile Safari/535.19'} r = requests.post(url, headers=headers) print （r.request.headers) #複雜post請求 url = 'http://m.ctrip.com' payload = {'some': 'data'} r = requests.post(url, data=json.dumps(payload)) #如果傳遞的payload是string而不是dict，需要先呼叫dumps方法格式化一下 # post多部分編碼檔案 url = 'http://m.ctrip.com' files = {'file': open('report.xls', 'rb')} r = requests.post(url, files=files) # 響應狀態碼 r = requests.get('http://m.ctrip.com') print(r.status_code) # 響應頭 r = requests.get('http://m.ctrip.com') print (r.headers) print (r.headers['Content-Type']) print (r.headers.get('content-type')) #訪問響應頭部分內容的兩種方式 # Cookies url = 'http://example.com/some/cookie/setting/url' r = requests.get(url) r.cookies['example_cookie_name'] #讀取cookies url = 'http://m.ctrip.com/cookies' cookies = dict(cookies_are='working') r = requests.get(url, cookies=cookies) #傳送cookies #設定超時時間 r = requests.get('http://m.ctrip.com', timeout=0.001) #設定訪問代理 proxies = { "http": "http://10.10.1.10:3128", "https": "http://10.10.1.100:4444", } r = requests.get('http://m.ctrip.com', proxies=proxies) #如果代理需要使用者名稱和密碼，則需要這樣： proxies = { "http": "http://user:[email protected]:3128/", }
3、示例程式碼
GET請求
# 1、無引數例項 import requests ret = requests.get('https://github.com/timeline.json') print(ret.url) print(ret.text) # 2、有引數例項 import requests payload = {'key1': 'value1', 'key2': 'value2'} ret = requests.get("http://httpbin.org/get", params=payload) print(ret.url) print(ret.text)
POST請求
# 1、基本POST例項 import requests payload = {'key1': 'value1', 'key2': 'value2'} ret = requests.post("http://httpbin.org/post", data=payload) print(ret.text) # 2、傳送請求頭和資料例項 import requests import json url = 'https://api.github.com/some/endpoint' payload = {'some': 'data'} headers = {'content-type': 'application/json'} ret = requests.post(url, data=json.dumps(payload), headers=headers) print(ret.text) print(ret.cookies)
請求引數
def request(method, url, **kwargs): """Constructs and sends a :class:`Request <Request>`. :param method: method for the new :class:`Request` object. :param url: URL for the new :class:`Request` object. :param params: (optional) Dictionary or bytes to be sent in the query string for the :class:`Request`. :param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`. :param json: (optional) json data to send in the body of the :class:`Request`. :param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`. :param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`. :param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': file-tuple}``) for multipart encoding upload. ``file-tuple`` can be a 2-tuple ``('filename', fileobj)``, 3-tuple ``('filename', fileobj, 'content_type')`` or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content-type'`` is a string defining the content type of the given file and ``custom_headers`` a dict-like object containing additional headers to add for the file. :param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth. :param timeout: (optional) How long to wait for the server to send data before giving up, as a float, or a :ref:`(connect timeout, read timeout) <timeouts>` tuple. :type timeout: float or tuple :param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed. :type allow_redirects: bool :param proxies: (optional) Dictionary mapping protocol to the URL of the proxy. :param verify: (optional) whether the SSL cert will be verified. A CA_BUNDLE path can also be provided. Defaults to ``True``. :param stream: (optional) if ``False``, the response content will be immediately downloaded. :param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair. :return: :class:`Response <Response>` object :rtype: requests.Response Usage:: >>> import requests >>> req = requests.request('GET', 'http://httpbin.org/get') <Response [200]> """
示例引數程式碼：
def param_method_url(): # requests.request(method='get', url='http://127.0.0.1:8000/test/') # requests.request(method='post', url='http://127.0.0.1:8000/test/') pass def param_param(): # - 可以是字典 # - 可以是字串 # - 可以是位元組（ascii編碼以內） # requests.request(method='get', # url='http://127.0.0.1:8000/test/', # params={'k1': 'v1', 'k2': '水電費'}) # requests.request(method='get', # url='http://127.0.0.1:8000/test/', # params="k1=v1&k2=水電費&k3=v3&k3=vv3") # requests.request(method='get', # url='http://127.0.0.1:8000/test/', # params=bytes("k1=v1&k2=k2&k3=v3&k3=vv3", encoding='utf8')) # 錯誤 # requests.request(method='get', # url='http://127.0.0.1:8000/test/', # params=bytes("k1=v1&k2=水電費&k3=v3&k3=vv3", encoding='utf8')) pass def param_data(): # 可以是字典 # 可以是字串 # 可以是位元組 # 可以是檔案物件 # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # data={'k1': 'v1', 'k2': '水電費'}) # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # data="k1=v1; k2=v2; k3=v3; k3=v4" # ) # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # data="k1=v1;k2=v2;k3=v3;k3=v4", # headers={'Content-Type': 'application/x-www-form-urlencoded'} # ) # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # data=open('data_file.py', mode='r', encoding='utf-8'), # 檔案內容是：k1=v1;k2=v2;k3=v3;k3=v4 # headers={'Content-Type': 'application/x-www-form-urlencoded'} # ) pass def param_json(): # 將json中對應的資料進行序列化成一個字串，json.dumps(...) # 然後傳送到伺服器端的body中，並且Content-Type是 {'Content-Type': 'application/json'} requests.request(method='POST', url='http://127.0.0.1:8000/test/', json={'k1': 'v1', 'k2': '水電費'}) def param_headers(): # 傳送請求頭到伺服器端 requests.request(method='POST', url='http://127.0.0.1:8000/test/', json={'k1': 'v1', 'k2': '水電費'}, headers={'Content-Type': 'application/x-www-form-urlencoded'} ) def param_cookies(): # 傳送Cookie到伺服器端 requests.request(method='POST', url='http://127.0.0.1:8000/test/', data={'k1': 'v1', 'k2': 'v2'}, cookies={'cook1': 'value1'}, ) # 也可以使用CookieJar（字典形式就是在此基礎上封裝） from http.cookiejar import CookieJar from http.cookiejar import Cookie obj = CookieJar() obj.set_cookie(Cookie(version=0, name='c1', value='v1', port=None, domain='', path='/', secure=False, expires=None, discard=True, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False, port_specified=False, domain_specified=False, domain_initial_dot=False, path_specified=False) ) requests.request(method='POST', url='http://127.0.0.1:8000/test/', data={'k1': 'v1', 'k2': 'v2'}, cookies=obj) def param_files(): # 傳送檔案 # file_dict = { # 'f1': open('readme', 'rb') # } # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # files=file_dict) # 傳送檔案，定製檔名 # file_dict = { # 'f1': ('test.txt', open('readme', 'rb')) # } # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # files=file_dict) # 傳送檔案，定製檔名 # file_dict = { # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf") # } # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # files=file_dict) # 傳送檔案，定製檔名 # file_dict = { # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf", 'application/text', {'k1': '0'}) # } # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # files=file_dict) pass def param_auth(): from requests.auth import HTTPBasicAuth, HTTPDigestAuth ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('wupeiqi', 'sdfasdfasdf')) print(ret.text) # ret = requests.get('http://192.168.1.1', # auth=HTTPBasicAuth('admin', 'admin')) # ret.encoding = 'gbk' # print(ret.text) # ret = requests.get('http://httpbin.org/digest-auth/auth/user/pass', auth=HTTPDigestAuth('user', 'pass')) # print(ret) # def param_timeout(): # ret = requests.get('http://google.com/', timeout=1) # print(ret) # ret = requests.get('http://google.com/', timeout=(5, 1)) # print(ret) pass def param_allow_redirects(): ret = requests.get('http://127.0.0.1:8000/test/', allow_redirects=False) print(ret.text) def param_proxies(): # proxies = { # "http": "61.172.249.96:80", # "https": "http://61.185.219.126:3128", # } # proxies = {'http://10.20.1.128': 'http://10.10.1.10:5323'} # ret = requests.get("http://www.proxy360.cn/Proxy", proxies=proxies) # print(ret.headers) # from requests.auth import HTTPProxyAuth # # proxyDict = { # 'http': '77.75.105.165', # 'https': '77.75.105.165' # } # auth = HTTPProxyAuth('username', 'mypassword') # # r = requests.get("http://www.google.com", proxies=proxyDict, auth=auth) # print(r.text) pass def param_stream(): ret = requests.get('http://127.0.0.1:8000/test/', stream=True) print(ret.content) ret.close() # from contextlib import closing # with closing(requests.get('http://httpbin.org/get', stream=True)) as r: # # 在此處理響應。 # for i in r.iter_content(): # print(i) def requests_session(): import requests session = requests.Session() ### 1、首先登陸任何頁面，獲取cookie i1 = session.get(url="http://dig.chouti.com/help/service") ### 2、使用者登陸，攜帶上一次的cookie，後臺對cookie中的 gpsd 進行授權 i2 = session.post( url="http://dig.chouti.com/login", data={ 'phone': "8615131255089", 'password': "xxxxxx", 'oneMonth': "" } ) i3 = session.post( url="http://dig.chouti.com/link/vote?linksId=8589623", ) print(i3.text)
json請求：
#! /usr/bin/python3 import requests import json class url_request(): def __init__(self): ''' init ''' if __name__ == '__main__': heard = {'Content-Type': 'application/json'} payload = {'CountryName': '中國', 'ProvinceName': '四川省', 'L1CityName': 'chengdu', 'L2CityName': 'yibing', 'TownName': '', 'Longitude': '107.33393', 'Latitude': '33.157131', 'Language': 'CN'} r = requests.post("http://www.xxxxxx.com/CityLocation/json/LBSLocateCity", heards=heard, data=payload) data = r.json() if r.status_code!=200: print('LBSLocateCity API Error' + str(r.status_code)) print(data['CityEntities'][0]['CityID']) # 列印返回json中的某個key的value print(data['ResponseStatus']['Ack']) print(json.dump(data, indent=4, sort_keys=True, ensure_ascii=False)) # 樹形列印json，ensure_ascii必須設為False否則中文會顯示為unicode
Xml請求：
#! /usr/bin/python3 import requests class url_request(): def __init__(self): """init""" if __name__ == '__main__': heards = {'Content-type': 'text/xml'} XML = '<?xml version="1.0" encoding="utf-8"?><soap:Envelope xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:soap="http://schemas.xmlsoap.org/soap/envelope/"><soap:Body><Request xmlns="http://tempuri.org/"><jme><JobClassFullName>WeChatJSTicket.JobWS.Job.JobRefreshTicket,WeChatJSTicket.JobWS</JobClassFullName><Action>RUN</Action><Param>1</Param><HostIP>127.0.0.1</HostIP><JobInfo>1</JobInfo><NeedParallel>false</NeedParallel></jme></Request></soap:Body></soap:Envelope>' url = 'http://jobws.push.mobile.xxxxxxxx.com/RefreshWeiXInTokenJob/RefreshService.asmx' r = requests.post(url=url, heards=heards, data=XML) data = r.text print(data)
狀態異常處理：
import requests URL = 'http://ip.taobao.com/service/getIpInfo.php' # 淘寶IP地址庫API try: r = requests.get(URL, params={'ip': '8.8.8.8'}, timeout=1) r.raise_for_status() # 如果響應狀態碼不是 200，就主動丟擲異常 except requests.RequestException as e: print(e) else: result = r.json() print(type(result), result, sep='\n')
上傳檔案：
import requests url = 'http://127.0.0.1:8080/upload' files = {'file': open('/home/rxf/test.jpg', 'rb')} #files = {'file': ('report.jpg', open('/home/lyb/sjzl.mpg', 'rb'))} #顯式的設定檔名 r = requests.post(url, files=files) print(r.text)
request更加方便的是，可以把字串當作檔案進行上傳：
import requests url = 'http://127.0.0.1:8080/upload' files = {'file': ('test.txt', b'Hello Requests.')} #必需顯式的設定檔名 r = requests.post(url, files=files) print(r.text)
身份驗證：
基本身份認證(HTTP Basic Auth)：
import requests from requests.auth import HTTPBasicAuth r = requests.get('https://httpbin.org/hidden-basic-auth/user/passwd', auth=HTTPBasicAuth('user', 'passwd')) # r = requests.get('https://httpbin.org/hidden-basic-auth/user/passwd', auth=('user', 'passwd')) # 簡寫 print(r.json())
另一種非常流行的HTTP身份認證形式是摘要式身份認證，Requests對它的支援也是開箱即可用的:
requests.get(URL, auth=HTTPDigestAuth('user', 'pass')
Cookies與會話物件：
如果某個響應中包含一些Cookie，你可以快速訪問它們：
import requests r = requests.get('http://www.google.com.hk/') print(r.cookies['NID']) print(tuple(r.cookies))
要想傳送你的cookies到伺服器，可以使用 cookies 引數：
import requests url = 'http://httpbin.org/cookies' cookies = {'testCookies_1': 'Hello_Python3', 'testCookies_2': 'Hello_Requests'} # 在Cookie Version 0中規定空格、方括號、圓括號、等於號、逗號、雙引號、斜槓、問號、@，冒號，分號等特殊符號都不能作為Cookie的內容。 r = requests.get(url, cookies=cookies) print(r.json())
會話物件讓你能夠跨請求保持某些引數，最方便的是在同一個Session例項發出的所有請求之間保持cookies，且這些都是自動處理的，甚是方便。
下面就來一個真正的例項，如下是快盤簽到指令碼：
import requests headers = {'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Accept-Encoding': 'gzip, deflate, compress', 'Accept-Language': 'en-us;q=0.5,en;q=0.3', 'Cache-Control': 'max-age=0', 'Connection': 'keep-alive', 'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:22.0) Gecko/20100101 Firefox/22.0'} s = requests.Session() s.headers.update(headers) # s.auth = ('superuser', '123') s.get('https://www.kuaipan.cn/account_login.htm') _URL = 'http://www.kuaipan.cn/index.php' s.post(_URL, params={'ac':'account', 'op':'login'}, data={'username':'****@foxmail.com', 'userpwd':'********', 'isajax':'yes'}) r = s.get(_URL, params={'ac':'zone', 'op':'taskdetail'}) print(r.json()) s.get(_URL, params={'ac':'common', 'op':'usersign'})
requests模組抓取網頁原始碼並儲存到檔案示例：
這是一個基本的檔案儲存操作，但這裡有幾個值得注意的問題：
1.安裝requests包，命令列輸入pip install requests即可自動安裝。很多人推薦使用requests，自帶的urllib.request也可以抓取網頁原始碼
2.open方法encoding引數設為utf-8，否則儲存的檔案會出現亂碼。
3.如果直接在cmd中輸出抓取的內容，會提示各種編碼錯誤，所以儲存到檔案檢視。
4.with open方法是更好的寫法，可以自動操作完畢後釋放資源
#! /urs/bin/python3 import requests '''requests模組抓取網頁原始碼並儲存到檔案示例''' html = requests.get("http://www.baidu.com") with open('test.txt', 'w', encoding='utf-8') as f: f.write(html.text) '''讀取一個txt檔案，每次讀取一行，並儲存到另一個txt檔案中的示例''' ff = open('testt.txt', 'w', encoding='utf-8') with open('test.txt', encoding="utf-8") as f: for line in f: ff.write(line) ff.close()
因為在命令列中列印每次讀取一行的資料，中文會出現編碼錯誤，所以每次讀取一行並儲存到另一個檔案，這樣來測試讀取是否正常。（注意open的時候制定encoding編碼方式）
自動登陸"示例：
抽屜新熱榜：
#!/usr/bin/env python # -*- coding:utf-8 -*- import requests # ############## 方式一 ############## """ # ## 1、首先登陸任何頁面，獲取cookie i1 = requests.get(url="http://dig.chouti.com/help/service") i1_cookies = i1.cookies.get_dict() # ## 2、使用者登陸，攜帶上一次的cookie，後臺對cookie中的 gpsd 進行授權 i2 = requests.post( url="http://dig.chouti.com/login", data={ 'phone': "8615131255089", 'password': "xxooxxoo", 'oneMonth': "" }, cookies=i1_cookies ) # ## 3、點贊（只需要攜帶已經被授權的gpsd即可） gpsd = i1_cookies['gpsd'] i3 = requests.post( url="http://dig.chouti.com/link/vote?linksId=8589523", cookies={'gpsd': gpsd} ) print(i3.text) """ # ############## 方式二 ############## """ import requests session = requests.Session() i1 = session.get(url="http://dig.chouti.com/help/service") i2 = session.post( url="http://dig.chouti.com/login", data={ 'phone': "8615131255089", 'password': "xxooxxoo", 'oneMonth': "" } ) i3 = session.post( url="http://dig.chouti.com/link/vote?linksId=8589523" ) print(i3.text) """
github：
#!/usr/bin/env python # -*- coding:utf-8 -*- import requests from bs4 import BeautifulSoup # ############## 方式一 ############## # # # 1. 訪問登陸頁面，獲取 authenticity_token # i1 = requests.get('https://github.com/login') # soup1 = BeautifulSoup(i1.text, features='lxml') # tag = soup1.find(name='input', attrs={'name': 'authenticity_token'}) # authenticity_token = tag.get('value') # c1 = i1.cookies.get_dict() # i1.close() # # # 1. 攜帶authenticity_token和使用者名稱密碼等資訊，傳送使用者驗證 # form_data = { # "authenticity_token": authenticity_token, # "utf8": "", # "commit": "Sign in", # "login": "[email protected]", # 'password': 'xxoo' # } # # i2 = requests.post('https://github.com/session', data=form_data, cookies=c1) # c2 = i2.cookies.get_dict() # c1.update(c2) # i3 = requests.get('https://github.com/settings/repositories', cookies=c1) # # soup3 = BeautifulSoup(i3.text, features='lxml') # list_group = soup3.find(name='div', class_='listgroup') # # from bs4.element import Tag # # for child in list_group.children: # if isinstance(child, Tag): # project_tag = child.find(name='a', class_='mr-1') # size_tag = child.find(name='small') # temp = "專案:%s(%s); 專案路徑:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, ) # print(temp) # ############## 方式二 ############## # session = requests.Session() # # 1. 訪問登陸頁面，獲取 authenticity_token # i1 = session.get('https://github.com/login') # soup1 = BeautifulSoup(i1.text, features='lxml') # tag = soup1.find(name='input', attrs={'name': 'authenticity_token'}) # authenticity_token = tag.get('value') # c1 = i1.cookies.get_dict() # i1.close() # # # 1. 攜帶authenticity_token和使用者名稱密碼等資訊，傳送使用者驗證 # form_data = { # "authenticity_token": authenticity_token, # "utf8": "", # "commit": "Sign in", # "login": "[email protected]", # 'password': 'xxoo' # } # # i2 = session.post('https://github.com/session', data=form_data) # c2 = i2.cookies.get_dict() # c1.update(c2) # i3 = session.get('https://github.com/settings/repositories') # # soup3 = BeautifulSoup(i3.text, features='lxml') # list_group = soup3.find(name='div', class_='listgroup') # # from bs4.element import Tag # # for child in list_group.children: # if isinstance(child, Tag): # project_tag = child.find(name='a', class_='mr-1') # size_tag = child.find(name='small') # temp = "專案:%s(%s); 專案路徑:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, ) # print(temp)
知乎：
#!/usr/bin/env python # -*- coding:utf-8 -*- import time import requests from bs4 import BeautifulSoup session = requests.Session() i1 = session.get( url='https://www.zhihu.com/#signin', headers={ 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36', } ) soup1 = BeautifulSoup(i1.text, 'lxml') xsrf_tag = soup1.find(name='input', attrs={'name': '_xsrf'}) xsrf = xsrf_tag.get('value') current_time = time.time() i2 = session.get( url='https://www.zhihu.com/captcha.gif', params={'r': current_time, 'type': 'login'}, headers={ 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36', }) with open('zhihu.gif', 'wb') as f: f.write(i2.content) captcha = input('請開啟zhihu.gif檔案，檢視並輸入驗證碼：') form_data = { "_xsrf": xsrf, 'password': 'xxooxxoo', "captcha": 'captcha', 'email': '[email protected]' } i3 = session.post( url='https://www.zhihu.com/login/email', data=form_data, headers={ 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36', } ) i4 = session.get( url='https://www.zhihu.com/settings/profile', headers={ 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36', } ) soup4 = BeautifulSoup(i4.text, 'lxml') tag = soup4.find(id='rename-section') nick_name = tag.find('span',class_='name').string print(nick_name)
部落格園：
#!/usr/bin/env python # -*- coding:utf-8 -*- import re import json import base64 import rsa import requests def js_encrypt(text): b64der = 'MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQCp0wHYbg/NOPO3nzMD3dndwS0MccuMeXCHgVlGOoYyFwLdS24Im2e7YyhB0wrUsyYf0/nhzCzBK8ZC9eCWqd0aHbdgOQT6CuFQBMjbyGYvlVYU2ZP7kG9Ft6YV6oc9ambuO7nPZh+bvXH0zDKfi02prknrScAKC0XhadTHT3Al0QIDAQAB' der = base64.standard_b64decode(b64der) pk = rsa.PublicKey.load_pkcs1_openssl_der(der) v1 = rsa.encrypt(bytes(text, 'utf8'), pk) value = base64.encodebytes(v1).replace(b'\n', b'') value = value.decode('utf8') return value session = requests.Session() i1 = session.get('https://passport.cnblogs.com/user/signin') rep = re.compile("'VerificationToken': '(.*)'") v = re.search(rep, i1.text) verification_token = v.group(1) form_data = { 'input1': js_encrypt('wptawy'), 'input2': js_encrypt('asdfasdf'), 'remember': False } i2 = session.post(url='https://passport.cnblogs.com/user/signin', data=json.dumps(form_data), headers={ 'Content-Type': 'application/json; charset=UTF-8', 'X-Requested-With': 'XMLHttpRequest', 'VerificationToken': verification_token} ) i3 = session.get(url='https://i.cnblogs.com/EditDiary.aspx') print(i3.text)
拉勾網：
#!/usr/bin/env python # -*- coding:utf-8 -*- import requests # 第一步：訪問登陸頁,拿到X_Anti_Forge_Token，X_Anti_Forge_Code # 1、請求url:https://passport.lagou.com/login/login.html # 2、請求方法:GET # 3、請求頭: # User-agent r1 = requests.get('https://passport.lagou.com/login/login.html', headers={ 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36', }, ) X_Anti_Forge_Token = re.findall("X_Anti_Forge_Token = '(.*?)'", r1.text, re.S)[0] X_Anti_Forge_Code = re.findall("X_Anti_Forge_Code = '(.*?)'", r1.text, re.S)[0] print(X_Anti_Forge_Token, X_Anti_Forge_Code) # print(r1.cookies.get_dict()) # 第二步：登陸 # 1、請求url:https://passport.lagou.com/login/login.json # 2、請求方法:POST # 3、請求頭: # cookie # User-agent # Referer:https://passport.lagou.com/login/login.html # X-Anit-Forge-Code:53165984 # X-Anit-Forge-Token:3b6a2f62-80f0-428b-8efb-ef72fc100d78 # X-Requested-With:XMLHttpRequest # 4、請求體： # isValidate:true # username:15131252215 # password:ab18d270d7126ea65915c50288c22c0d # request_form_verifyCode:'' # submit:'' r2 = requests.post( 'https://passport.lagou.com/login/login.json', headers={ 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36', 'Referer': 'https://passport.lagou.com/login/login.html', 'X-Anit-Forge-Code': X_Anti_Forge_Code, 'X-Anit-Forge-Token': X_Anti_Forge_Token, 'X-Requested-With': 'XMLHttpRequest' }, data={ "isValidate": True, 'username': '15131255089', 'password': 'ab18d270d7126ea65915c50288c22c0d', 'request_form_verifyCode': '', 'submit': '' }, cookies=r1.cookies.get_dict() ) print(r2.text)去期待陌生，去擁抱驚喜。